pyabsa.tasks.AspectSentimentTripletExtraction.instructor.instructor¶
Classes¶
Module Contents¶
- class pyabsa.tasks.AspectSentimentTripletExtraction.instructor.instructor.ASTETrainingInstructor(config)¶
Bases:
pyabsa.framework.instructor_class.instructor_template.BaseTrainingInstructor- _load_dataset_and_prepare_dataloader()¶
Load the dataset and prepare the dataloader. This method should be implemented in a subclass.
- _prepare_dataloader()¶
Prepares the data loaders for training, validation, and testing. Special for ASTE, do not use the default data loader
- _train_and_evaluate(criterion)¶
Train and evaluate the model. This method should be implemented in a subclass.
- _k_fold_train_and_evaluate(criterion)¶
Train and evaluate the model using k-fold cross validation. This method should be implemented in a subclass.
- _evaluate_f1(data_loader, FLAG=False)¶
- _init_misc()¶
Initialize miscellaneous settings specific to the subclass implementation. This method should be implemented in a subclass.
- run()¶
- _train(criterion)¶
Train the model on a given criterion.
- Parameters:
criterion – The loss function used to train the model.
- Returns:
If there is only one validation dataloader, return the training results. If there are more than one validation dataloaders, perform k-fold cross-validation and return the results.